Integrating machine learning algorithms and remote sensing for High-Resolution mapping of soil crusting in
Fengwei Zhang1,2,3,4, Xinghua Qi5,6,7, Ming Xiang5,6,7
1Key Laboratory of Xinjiang Coal Resources Green Mining (Xinjiang Institute of Engineering), Ministry of Education, Urumqi, 830023, China. xjgcxyzfw@163.com.
Soil crusting, a form of land degradation, was mapped using machine learning in China. The Random Forest model accurately predicted soil crusting, identifying clay content as a key factor for mitigation strategies in agricultural lands.
Area of Science:
- Environmental Science
- Soil Science
- Remote Sensing
Background:
- Soil crusting is a major land degradation issue impacting agricultural productivity and soil health.
- Identifying and managing degraded areas is crucial for sustainable agriculture.
Purpose of the Study:
- To assess soil crusting in agricultural lands using machine learning.
- To compare the performance of Random Forest (RF) and Multiple Linear Regression (MLR) models.
- To identify key predictors of soil crusting.
Main Methods:
- Collected 520 soil samples from agricultural lands in Shaanxi Province, China.
- Calculated the Soil Crusting Index (SCI) for each sample.
- Utilized 26 digital elevation model indices and 13 remote sensing datasets.
- Applied and compared RF and MLR machine learning algorithms.
Main Results:
- Soil Crusting Index (SCI) values ranged from 0.27 to 2.69, with higher susceptibility in northeastern areas.
- The RF model significantly outperformed MLR, achieving R² = 0.79 and lower RMSE (0.161).
- The Clay Index (CI) was the most influential predictor, followed by precipitation, runoff, and vegetation factors.
Conclusions:
- Machine learning, particularly RF, is effective for mapping soil crusting in agricultural lands.
- Clay content is a primary driver of soil crusting, alongside hydrological and vegetation factors.
- Hybrid modeling approaches are recommended for future soil crusting prediction and management strategies.
More Related Videos
08:09Measuring and Mapping Patterns of Soil Erosion and Deposition Related to Soil Carbonate Concentrations Under Agricultural Management
Published on: September 12, 2017
09:44Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
Published on: October 16, 2018
Related Concept Videos
Topographic Surveying and Contours
Methods of Obtaining Topography
Types of Global Positioning System Surveys
Design Example: Identifying the Locations of Monuments in the Field Using Global Positioning System Device
Manipulation and Analysis
Application of Linearization and Approximation
